Invited Talks and Seminars

Yaneva, V. 2024. LLMs and Educational Assessment in medicine: Is generating clinically accurate test content within reach? Invited talk at AAAI2024 Workshop on AI for Education – Bridging Innovation and Responsibility. Vancouver, Canada (2/27/2024)

Yaneva, V. 2023. Extracting Linguistic Signal from Item Text and Its Application to Modeling Item Characteristics. CanAm Online Symposium, University of Alberta, Canada. Virtual (12/08/2023)

Yaneva, V. 2023. Improving Web Accessibility for Adults with Autism: Insights from Surveys and Eye-Tracking Experiments. Keynote at TSAR’23 (Second Workshop on Text Simplification, Accessibility and Readability). Varna, Bulgaria (07/09/2023) 

Yaneva, V. 2023. Automated Scoring of Clinical Patient Notes: Findings From NBME’s Kaggle Competition and Their Translation into Practice. Seminar series at Educational Testing Service (ETS). Princeton, USA (18/06/2023)

Yaneva, V. 2023. Automated Scoring of Clinical Patient Notes: Findings From NBME’s Kaggle Competition and Their Translation into Practice. Seminar series at National Research Council Canada / Conseil national de recherches Canada. Virtual (12/05/2023)

Yaneva, V. 2023. Examining chatGPT Performance on USMLE Practice Items and Implications for Medical Assessment. Invited Panel Symposium “From Science Fiction to 2023’s GPT-4: Implications for Assessment”. National Council of Measurement in Education (NCME), Chicago, USA (04/13/2023)

Yaneva, V. 2022. Extracting Linguistic Signal from Item Text and Its Application to Modeling Item Characteristics. Virtual Brown Bag Speaker Series on Natural Language Processing (NLP) & Artificial Intelligence (AI) in Education, Boston College. Virtual (12/10/2022)

Yaneva, V. 2022. Extracting Linguistic Signal from Item Text and Its Application to Modeling Item Characteristics. Assessment Research Speaker Series, Duolingo. Virtual (28/07/2022)

Yaneva, V. 2021. Eye-Tracking Evidence for Visual Processing Differences
Can Aid Automated Autism Detection and Make the Web
More Accessible. Department of Computer and Information Sciences, Temple University. Philadelphia, USA (12/05/2021). Abstract PDF

Yaneva, V. 2019. Predicting the Difficulty of Multiple-Choice Questions for a High-Stakes Medical Exam. Department of Computer Science, University of Manchester. Manchester, UK.  (28/08/2019)

Yaneva, V. 2019. Applying Behavioural Data to NLP Models for Solving Ambiguity and Non-compositionality. Institute for Logic, Language, and Computation, University of Amsterdam. Amsterdam, Netherlands. (12/03/2019)

Yaneva, V. 2017. Do You See What I Mean? The Use of Eye Tracking Data in Readability and Accessibility Research. Université Catholique de Louvain. Louvain-la-Neuve, Belgium.

Oral Presentations 

• Helping Item Writers by Making NLP-Based Suggestions for Item Distractors. Peter Baldwin, Victoria Yaneva, Janet Mee, Brian Clauser & Le An Ha
• On the Utility of Using Transfer Learning to Predict Item Characteristics. Kang Xue, Victoria Yaneva & Christopher Runyon 

NCME/AERA 2019

• Predicting Item Survival Using Natural Language Processing. Victoria Yaneva, Le An Ha, Peter Baldwin and Janet Mee. Annual Meeting of the National Council on Measurement in Education (NCME), April 4-8, Toronto, Canada.
• On the Relationship Between Item Characteristics and Linguistically Motivated Item Features. Janet Mee, Peter Baldwin, Le An Ha and Victoria Yaneva (2019, April). Annual Convention of the American Educational Research Association, Toronto, Canada.

Other talks

Yaneva, V.  2017. AI for Accessibility: The Case of Autism. At the BrumAI Society meeting. Birmingham, UK

Yaneva, V.  2015.  The Way People with Autism Understand Language. At The Autism Show: The National Event for Autism, ExCeL Centre. London, UK.

Yaneva, V. 2015. Reducing the effects of ASD-specific situational variables . At the Autism and the Foundations of Language and Communication conference. Dublin, Ireland.